Synthesizing Complex-Valued Multicoil MRI Data from Magnitude-Only Images

Abstract

Despite the proliferation of deep learning techniques for accelerated MRI acquisition and enhanced image reconstruction, the construction of large and diverse MRI datasets continues to pose a barrier to effective clinical translation of these technologies. One major challenge is in collecting the MRI raw data (required for image reconstruction) from clinical scanning, as only magnitude images are typically saved and used for clinical assessment and diagnosis. The image phase and multi-channel RF coil information are not retained when magnitude-only images are saved in clinical imaging archives. Additionally, preprocessing used for data in clinical imaging can lead to biased results. While several groups have begun concerted efforts to collect large amounts of MRI raw data, current databases are limited in the diversity of anatomy, pathology, annotations, and acquisition types they contain. To address this, we present a method for synthesizing realistic MR data from magnitude-only data, allowing for the use of diverse data from clinical imaging archives in advanced MRI reconstruction development. Our method uses a conditional GAN-based framework to generate synthetic phase images from input magnitude images. We then applied ESPIRiT to derive RF coil sensitivity maps from fully sampled real data to generate multi-coil data. The synthetic data generation method was evaluated by comparing image reconstruction results from training Variational Networks either with real data or synthetic data. We demonstrate that the Variational Network trained on synthetic MRI data from our method, consisting of GAN-derived synthetic phase and multi-coil information, outperformed Variational Networks trained on data with synthetic phase generated using current state-of-the-art methods. Additionally, we demonstrate that the Variational Networks trained with synthetic k-space data from our method perform comparably to image reconstruction networks trained on undersampled real k-space data.

AI in MRI: Computational Frameworks for a Faster, Optimized, and Automated Imaging Workflow

“…First, the emergence of methods for addressing the lack or scarcity of open-access training data, a known obstacle for algorithm development [ 73 ]. Here, this challenge was addressed using data-style transfer [ 74 ], manifold learning directly from undersampled dynamic MRI data [ 53 ], complex-valued data synthesis with GANs [ 49 ], pre-training on “pretext tasks” [ 75 ], and federated learning [ 50 ]. The second trend is the shift towards more comprehensive AI pipelines, which aim to address more than one component of the MRI workflow.…”

“…Experiments with cardiac data indicate that SelCoLearn produces high-quality reconstructions of dynamic MRI data. Additionally, Deveshwar et al [ 49 ] introduce a method for synthesizing multi-coil complex-valued data from magnitude-only data; this can be useful for leveraging the high number of DICOM images that are stored in clinical databases. Their method uses conditional generative adversarial networks (GANs) for generating synthetic-phase images and ESPIRiT [ 28 ] for generating sensitivity maps from publicly available databases.…”